Skip to content

Commit

Permalink
Add MuJoCo v5 environments (#572)
Browse files Browse the repository at this point in the history
  • Loading branch information
@Kallinteris-Andreas
Kallinteris-Andreas authored Jul 24, 2023
1 parent 40822a9 commit 0736be9
Show file tree
Hide file tree
Showing 26 changed files with 4,546 additions and 1,589 deletions.
80 changes: 79 additions & 1 deletion gymnasium/envs/__init__.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,7 @@
# Mujoco
# ----------------------------------------

# 2D
# manipulation

register(
id="Reacher-v2",
Expand All @@ -196,6 +196,13 @@
reward_threshold=-3.75,
)

register(
id="Reacher-v5",
entry_point="gymnasium.envs.mujoco.reacher_v5:ReacherEnv",
max_episode_steps=50,
reward_threshold=-3.75,
)

register(
id="Pusher-v2",
entry_point="gymnasium.envs.mujoco:PusherEnv",
Expand All @@ -210,6 +217,15 @@
reward_threshold=0.0,
)

register(
id="Pusher-v5",
entry_point="gymnasium.envs.mujoco.pusher_v5:PusherEnv",
max_episode_steps=100,
reward_threshold=0.0,
)

# balance

register(
id="InvertedPendulum-v2",
entry_point="gymnasium.envs.mujoco:InvertedPendulumEnv",
Expand All @@ -224,6 +240,13 @@
reward_threshold=950.0,
)

register(
id="InvertedPendulum-v5",
entry_point="gymnasium.envs.mujoco.inverted_pendulum_v5:InvertedPendulumEnv",
max_episode_steps=1000,
reward_threshold=950.0,
)

register(
id="InvertedDoublePendulum-v2",
entry_point="gymnasium.envs.mujoco:InvertedDoublePendulumEnv",
Expand All @@ -238,6 +261,15 @@
reward_threshold=9100.0,
)

register(
id="InvertedDoublePendulum-v5",
entry_point="gymnasium.envs.mujoco.inverted_double_pendulum_v5:InvertedDoublePendulumEnv",
max_episode_steps=1000,
reward_threshold=9100.0,
)

# runners

register(
id="HalfCheetah-v2",
entry_point="gymnasium.envs.mujoco:HalfCheetahEnv",
Expand All @@ -259,6 +291,13 @@
reward_threshold=4800.0,
)

register(
id="HalfCheetah-v5",
entry_point="gymnasium.envs.mujoco.half_cheetah_v5:HalfCheetahEnv",
max_episode_steps=1000,
reward_threshold=4800.0,
)

register(
id="Hopper-v2",
entry_point="gymnasium.envs.mujoco:HopperEnv",
Expand All @@ -280,6 +319,13 @@
reward_threshold=3800.0,
)

register(
id="Hopper-v5",
entry_point="gymnasium.envs.mujoco.hopper_v5:HopperEnv",
max_episode_steps=1000,
reward_threshold=3800.0,
)

register(
id="Swimmer-v2",
entry_point="gymnasium.envs.mujoco:SwimmerEnv",
Expand All @@ -301,6 +347,13 @@
reward_threshold=360.0,
)

register(
id="Swimmer-v5",
entry_point="gymnasium.envs.mujoco.swimmer_v5:SwimmerEnv",
max_episode_steps=1000,
reward_threshold=360.0,
)

register(
id="Walker2d-v2",
max_episode_steps=1000,
Expand All @@ -319,6 +372,12 @@
entry_point="gymnasium.envs.mujoco.walker2d_v4:Walker2dEnv",
)

register(
id="Walker2d-v5",
max_episode_steps=1000,
entry_point="gymnasium.envs.mujoco.walker2d_v5:Walker2dEnv",
)

register(
id="Ant-v2",
entry_point="gymnasium.envs.mujoco:AntEnv",
Expand All @@ -340,6 +399,13 @@
reward_threshold=6000.0,
)

register(
id="Ant-v5",
entry_point="gymnasium.envs.mujoco.ant_v5:AntEnv",
max_episode_steps=1000,
reward_threshold=6000.0,
)

register(
id="Humanoid-v2",
entry_point="gymnasium.envs.mujoco:HumanoidEnv",
Expand All @@ -358,6 +424,12 @@
max_episode_steps=1000,
)

register(
id="Humanoid-v5",
entry_point="gymnasium.envs.mujoco.humanoid_v5:HumanoidEnv",
max_episode_steps=1000,
)

register(
id="HumanoidStandup-v2",
entry_point="gymnasium.envs.mujoco:HumanoidStandupEnv",
Expand All @@ -370,6 +442,12 @@
max_episode_steps=1000,
)

register(
id="HumanoidStandup-v5",
entry_point="gymnasium.envs.mujoco.humanoidstandup_v5:HumanoidStandupEnv",
max_episode_steps=1000,
)


# --- For shimmy compatibility
def _raise_shimmy_error(*args: Any, **kwargs: Any):
Expand Down
187 changes: 0 additions & 187 deletions gymnasium/envs/mujoco/ant_v4.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,193 +11,6 @@


class AntEnv(MujocoEnv, utils.EzPickle):
"""
## Description
This environment is based on the environment introduced by Schulman,
Moritz, Levine, Jordan and Abbeel in ["High-Dimensional Continuous Control
Using Generalized Advantage Estimation"](https://arxiv.org/abs/1506.02438).
The ant is a 3D robot consisting of one torso (free rotational body) with
four legs attached to it with each leg having two body parts. The goal is to
coordinate the four legs to move in the forward (right) direction by applying
torques on the eight hinges connecting the two body parts of each leg and the torso
(nine body parts and eight hinges).
## Action Space
The action space is a `Box(-1, 1, (8,), float32)`. An action represents the torques applied at the hinge joints.
| Num | Action | Control Min | Control Max | Name (in corresponding XML file) | Joint | Unit |
| --- | ----------------------------------------------------------------- | ----------- | ----------- | -------------------------------- | ----- | ------------ |
| 0 | Torque applied on the rotor between the torso and back right hip | -1 | 1 | hip_4 (right_back_leg) | hinge | torque (N m) |
| 1 | Torque applied on the rotor between the back right two links | -1 | 1 | angle_4 (right_back_leg) | hinge | torque (N m) |
| 2 | Torque applied on the rotor between the torso and front left hip | -1 | 1 | hip_1 (front_left_leg) | hinge | torque (N m) |
| 3 | Torque applied on the rotor between the front left two links | -1 | 1 | angle_1 (front_left_leg) | hinge | torque (N m) |
| 4 | Torque applied on the rotor between the torso and front right hip | -1 | 1 | hip_2 (front_right_leg) | hinge | torque (N m) |
| 5 | Torque applied on the rotor between the front right two links | -1 | 1 | angle_2 (front_right_leg) | hinge | torque (N m) |
| 6 | Torque applied on the rotor between the torso and back left hip | -1 | 1 | hip_3 (back_leg) | hinge | torque (N m) |
| 7 | Torque applied on the rotor between the back left two links | -1 | 1 | angle_3 (back_leg) | hinge | torque (N m) |
## Observation Space
Observations consist of positional values of different body parts of the ant,
followed by the velocities of those individual parts (their derivatives) with all
the positions ordered before all the velocities.
By default, observations do not include the x- and y-coordinates of the ant's torso. These may
be included by passing `exclude_current_positions_from_observation=False` during construction.
In that case, the observation space will be a `Box(-Inf, Inf, (29,), float64)` where the first two observations
represent the x- and y- coordinates of the ant's torso.
Regardless of whether `exclude_current_positions_from_observation` was set to true or false, the x- and y-coordinates
of the torso will be returned in `info` with keys `"x_position"` and `"y_position"`, respectively.
However, by default, observation Space is a `Box(-Inf, Inf, (27,), float64)` where the elements correspond to the following:
| Num | Observation | Min | Max | Name (in corresponding XML file) | Joint | Unit |
|-----|--------------------------------------------------------------|--------|--------|----------------------------------------|-------|--------------------------|
| 0 | z-coordinate of the torso (centre) | -Inf | Inf | torso | free | position (m) |
| 1 | x-orientation of the torso (centre) | -Inf | Inf | torso | free | angle (rad) |
| 2 | y-orientation of the torso (centre) | -Inf | Inf | torso | free | angle (rad) |
| 3 | z-orientation of the torso (centre) | -Inf | Inf | torso | free | angle (rad) |
| 4 | w-orientation of the torso (centre) | -Inf | Inf | torso | free | angle (rad) |
| 5 | angle between torso and first link on front left | -Inf | Inf | hip_1 (front_left_leg) | hinge | angle (rad) |
| 6 | angle between the two links on the front left | -Inf | Inf | ankle_1 (front_left_leg) | hinge | angle (rad) |
| 7 | angle between torso and first link on front right | -Inf | Inf | hip_2 (front_right_leg) | hinge | angle (rad) |
| 8 | angle between the two links on the front right | -Inf | Inf | ankle_2 (front_right_leg) | hinge | angle (rad) |
| 9 | angle between torso and first link on back left | -Inf | Inf | hip_3 (back_leg) | hinge | angle (rad) |
| 10 | angle between the two links on the back left | -Inf | Inf | ankle_3 (back_leg) | hinge | angle (rad) |
| 11 | angle between torso and first link on back right | -Inf | Inf | hip_4 (right_back_leg) | hinge | angle (rad) |
| 12 | angle between the two links on the back right | -Inf | Inf | ankle_4 (right_back_leg) | hinge | angle (rad) |
| 13 | x-coordinate velocity of the torso | -Inf | Inf | torso | free | velocity (m/s) |
| 14 | y-coordinate velocity of the torso | -Inf | Inf | torso | free | velocity (m/s) |
| 15 | z-coordinate velocity of the torso | -Inf | Inf | torso | free | velocity (m/s) |
| 16 | x-coordinate angular velocity of the torso | -Inf | Inf | torso | free | angular velocity (rad/s) |
| 17 | y-coordinate angular velocity of the torso | -Inf | Inf | torso | free | angular velocity (rad/s) |
| 18 | z-coordinate angular velocity of the torso | -Inf | Inf | torso | free | angular velocity (rad/s) |
| 19 | angular velocity of angle between torso and front left link | -Inf | Inf | hip_1 (front_left_leg) | hinge | angle (rad) |
| 20 | angular velocity of the angle between front left links | -Inf | Inf | ankle_1 (front_left_leg) | hinge | angle (rad) |
| 21 | angular velocity of angle between torso and front right link | -Inf | Inf | hip_2 (front_right_leg) | hinge | angle (rad) |
| 22 | angular velocity of the angle between front right links | -Inf | Inf | ankle_2 (front_right_leg) | hinge | angle (rad) |
| 23 | angular velocity of angle between torso and back left link | -Inf | Inf | hip_3 (back_leg) | hinge | angle (rad) |
| 24 | angular velocity of the angle between back left links | -Inf | Inf | ankle_3 (back_leg) | hinge | angle (rad) |
| 25 | angular velocity of angle between torso and back right link | -Inf | Inf | hip_4 (right_back_leg) | hinge | angle (rad) |
| 26 | angular velocity of the angle between back right links | -Inf | Inf | ankle_4 (right_back_leg) | hinge | angle (rad) |
| excluded | x-coordinate of the torso (centre) | -Inf | Inf | torso | free | position (m) |
| excluded | y-coordinate of the torso (centre) | -Inf | Inf | torso | free | position (m) |
If version < `v4` or `use_contact_forces` is `True` then the observation space is extended by 14*6 = 84 elements, which are contact forces
(external forces - force x, y, z and torque x, y, z) applied to the
center of mass of each of the body parts. The 14 body parts are:
| id (for `v2`, `v3`, `v4)` | body parts |
| --- | ------------ |
| 0 | worldbody (note: forces are always full of zeros) |
| 1 | torso |
| 2 | front_left_leg |
| 3 | aux_1 (front left leg) |
| 4 | ankle_1 (front left leg) |
| 5 | front_right_leg |
| 6 | aux_2 (front right leg) |
| 7 | ankle_2 (front right leg) |
| 8 | back_leg (back left leg) |
| 9 | aux_3 (back left leg) |
| 10 | ankle_3 (back left leg) |
| 11 | right_back_leg |
| 12 | aux_4 (back right leg) |
| 13 | ankle_4 (back right leg) |
The (x,y,z) coordinates are translational DOFs while the orientations are rotational
DOFs expressed as quaternions. One can read more about free joints on the [Mujoco Documentation](https://mujoco.readthedocs.io/en/latest/XMLreference.html).
**Note:** Ant-v4 environment no longer has the following contact forces issue.
If using previous Humanoid versions from v4, there have been reported issues that using a Mujoco-Py version > 2.0 results
in the contact forces always being 0. As such we recommend to use a Mujoco-Py version < 2.0
when using the Ant environment if you would like to report results with contact forces (if
contact forces are not used in your experiments, you can use version > 2.0).
## Rewards
The reward consists of three parts:
- *healthy_reward*: Every timestep that the ant is healthy (see definition in section "Episode Termination"), it gets a reward of fixed value `healthy_reward`
- *forward_reward*: A reward of moving forward which is measured as
*(x-coordinate before action - x-coordinate after action)/dt*. *dt* is the time
between actions and is dependent on the `frame_skip` parameter (default is 5),
where the frametime is 0.01 - making the default *dt = 5 * 0.01 = 0.05*.
This reward would be positive if the ant moves forward (in positive x direction).
- *ctrl_cost*: A negative reward for penalising the ant if it takes actions
that are too large. It is measured as *`ctrl_cost_weight` * sum(action<sup>2</sup>)*
where *`ctr_cost_weight`* is a parameter set for the control and has a default value of 0.5.
- *contact_cost*: A negative reward for penalising the ant if the external contact
force is too large. It is calculated *`contact_cost_weight` * sum(clip(external contact
force to `contact_force_range`)<sup>2</sup>)*.
The total reward returned is ***reward*** *=* *healthy_reward + forward_reward - ctrl_cost*.
But if `use_contact_forces=True` or version < `v4`
The total reward returned is ***reward*** *=* *healthy_reward + forward_reward - ctrl_cost - contact_cost*.
In either case `info` will also contain the individual reward terms.
## Starting State
All observations start in state
(0.0, 0.0, 0.75, 1.0, 0.0 ... 0.0) with a uniform noise in the range
of [-`reset_noise_scale`, `reset_noise_scale`] added to the positional values and standard normal noise
with mean 0 and standard deviation `reset_noise_scale` added to the velocity values for
stochasticity. Note that the initial z coordinate is intentionally selected
to be slightly high, thereby indicating a standing up ant. The initial orientation
is designed to make it face forward as well.
## Episode End
The ant is said to be unhealthy if any of the following happens:
1. Any of the state space values is no longer finite
2. The z-coordinate of the torso is **not** in the closed interval given by `healthy_z_range` (defaults to [0.2, 1.0])
If `terminate_when_unhealthy=True` is passed during construction (which is the default),
the episode ends when any of the following happens:
1. Truncation: The episode duration reaches a 1000 timesteps
2. Termination: The ant is unhealthy
If `terminate_when_unhealthy=False` is passed, the episode is ended only when 1000 timesteps are exceeded.
## Arguments
No additional arguments are currently supported in v2 and lower.
```python
import gymnasium as gym
env = gym.make('Ant-v2')
```
v3 and v4 take `gymnasium.make` kwargs such as `xml_file`, `ctrl_cost_weight`, `reset_noise_scale`, etc.
```python
import gymnasium as gym
env = gym.make('Ant-v4', ctrl_cost_weight=0.1, ...)
```
| Parameter | Type | Default |Description |
|-------------------------|------------|--------------|-------------------------------|
| `xml_file` | **str** | `"ant.xml"` | Path to a MuJoCo model |
| `ctrl_cost_weight` | **float** | `0.5` | Weight for *ctrl_cost* term (see section on reward) |
| `use_contact_forces` | **bool** | `False` | If true, it extends the observation space by adding contact forces (see `Observation Space` section) and includes contact_cost to the reward function (see `Rewards` section) |
| `contact_cost_weight` | **float** | `5e-4` | Weight for *contact_cost* term (see section on reward) |
| `healthy_reward` | **float** | `1` | Constant reward given if the ant is "healthy" after timestep |
| `terminate_when_unhealthy` | **bool**| `True` | If true, issue a done signal if the z-coordinate of the torso is no longer in the `healthy_z_range` |
| `healthy_z_range` | **tuple** | `(0.2, 1)` | The ant is considered healthy if the z-coordinate of the torso is in this range |
| `contact_force_range` | **tuple** | `(-1, 1)` | Contact forces are clipped to this range in the computation of *contact_cost* |
| `reset_noise_scale` | **float** | `0.1` | Scale of random perturbations of initial position and velocity (see section on Starting State) |
| `exclude_current_positions_from_observation`| **bool** | `True`| Whether or not to omit the x- and y-coordinates from observations. Excluding the position can serve as an inductive bias to induce position-agnostic behavior in policies |
## Version History
* v4: All MuJoCo environments now use the MuJoCo bindings in mujoco >= 2.1.3, also removed contact forces from the default observation space (new variable `use_contact_forces=True` can restore them)
* v3: Support for `gymnasium.make` kwargs such as `xml_file`, `ctrl_cost_weight`, `reset_noise_scale`, etc. rgb rendering comes from tracking camera (so agent does not run away from screen)
* v2: All continuous control environments now use mujoco-py >= 1.50
* v1: max_time_steps raised to 1000 for robot based tasks. Added reward_threshold to environments.
* v0: Initial versions release (1.0.0)
"""

metadata = {
"render_modes": [
"human",
Expand Down
Loading

0 comments on commit 0736be9

Please sign in to comment.